English
Related papers

Related papers: Depth creates no more spurious local minima

200 papers

The past decade has witnessed a successful application of deep learning to solving many challenging problems in machine learning and artificial intelligence. However, the loss functions of deep neural networks (especially nonlinear…

Machine Learning · Statistics 2017-10-23 Yi Zhou , Yingbin Liang

We study the error landscape of deep linear and nonlinear neural networks with the squared error loss. Minimizing the loss of a deep linear neural network is a nonconvex problem, and despite recent progress, our understanding of this loss…

Machine Learning · Computer Science 2018-03-28 Chulhee Yun , Suvrit Sra , Ali Jadbabaie

We generalize recent theoretical work on the minimal number of layers of narrow deep belief networks that can approximate any probability distribution on the states of their visible units arbitrarily well. We relax the setting of binary…

Machine Learning · Statistics 2014-01-30 Guido F. Montúfar

Soft-thresholding has been widely used in neural networks. Its basic network structure is a two-layer convolution neural network with soft-thresholding. Due to the network's nature of nonlinearity and nonconvexity, the training process…

Machine Learning · Computer Science 2023-04-17 Chunyan Xiong , Mengli Lu , Xiaotong Yu , Jian Cao , Zhong Chen , Di Guo , Xiaobo Qu

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

Training neural networks involves finding minima of a high-dimensional non-convex loss function. Knowledge of the structure of this energy landscape is sparse. Relaxing from linear interpolations, we construct continuous paths between…

Machine Learning · Statistics 2019-02-25 Felix Draxler , Kambis Veschgini , Manfred Salmhofer , Fred A. Hamprecht

We give a new algorithm for learning a two-layer neural network under a general class of input distributions. Assuming there is a ground-truth two-layer network $$ y = A \sigma(Wx) + \xi, $$ where $A,W$ are weight matrices, $\xi$ represents…

Machine Learning · Computer Science 2019-02-05 Rong Ge , Rohith Kuditipudi , Zhize Li , Xiang Wang

We examine the squared error loss landscape of shallow linear neural networks. We show---with significantly milder assumptions than previous works---that the corresponding optimization problems have benign geometric properties: there are no…

Machine Learning · Computer Science 2018-11-06 Zhihui Zhu , Daniel Soudry , Yonina C. Eldar , Michael B. Wakin

In this paper we analyze the classification performance of neural network structures without parametric inference. Making use of neural architecture search, we empirically demonstrate that it is possible to find random weight architectures,…

Machine Learning · Computer Science 2021-04-15 Martin Mundt , Iuliia Pliushch , Visvanathan Ramesh

The optimization foundations of deep linear networks have recently received significant attention. However, due to their inherent non-convexity and hierarchical structure, analyzing the loss functions of deep linear networks remains a…

Optimization and Control · Mathematics 2025-09-24 Po Chen , Rujun Jiang , Peng Wang

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

This paper provides a least squares formulation for the training of a 2-layer convolutional neural network using quadratic activation functions, a 2-norm loss function, and no regularization term. Using this method, an analytic expression…

Machine Learning · Computer Science 2024-11-18 Zachary Yetman Van Egmond , Luis Rodrigues

Understanding deep neural networks is a major research objective with notable experimental and theoretical attention in recent years. The practical success of excessively large networks underscores the need for better theoretical analyses…

Machine Learning · Statistics 2022-03-10 Chiyuan Zhang , Samy Bengio , Yoram Singer

Can a neural network minimizing cross-entropy learn linearly separable data? Despite progress in the theory of deep learning, this question remains unsolved. Here we prove that SGD globally optimizes this learning problem for a two-layer…

Machine Learning · Computer Science 2021-07-29 Roei Sarussi , Alon Brutzkus , Amir Globerson

Learning Bayesian networks from raw data can help provide insights into the relationships between variables. While real data often contains a mixture of discrete and continuous-valued variables, many Bayesian network structure learning…

Artificial Intelligence · Computer Science 2018-09-19 Yi-Chun Chen , Tim Allan Wheeler , Mykel John Kochenderfer

Despite their empirical success, neural networks remain vulnerable to small, adversarial perturbations. A longstanding hypothesis suggests that flat minima, regions of low curvature in the loss landscape, offer increased robustness. While…

Machine Learning · Computer Science 2025-10-17 Nils Philipp Walter , Linara Adilova , Jilles Vreeken , Michael Kamp

While the universal approximation property holds both for hierarchical and shallow networks, we prove that deep (hierarchical) networks can approximate the class of compositional functions with the same accuracy as shallow networks but with…

Machine Learning · Computer Science 2016-05-31 Hrushikesh Mhaskar , Qianli Liao , Tomaso Poggio

It is widely observed that deep learning models with learned parameters generalize well, even with much more model parameters than the number of training samples. We systematically investigate the underlying reasons why deep neural networks…

Machine Learning · Computer Science 2017-11-29 Lei Wu , Zhanxing Zhu , Weinan E

Despite the fact that the loss functions of deep neural networks are highly non-convex, gradient-based optimization algorithms converge to approximately the same performance from many random initial points. One thread of work has focused on…

Machine Learning · Computer Science 2020-03-24 Charles G. Frye , James Simon , Neha S. Wadia , Andrew Ligeralde , Michael R. DeWeese , Kristofer E. Bouchard

In this paper, we show that although the minimizers of cross-entropy and related classification losses are off at infinity, network weights learned by gradient flow converge in direction, with an immediate corollary that network…

Machine Learning · Computer Science 2020-10-27 Ziwei Ji , Matus Telgarsky